The JUSThink project aims to improve the computational thinking skills of children by exercising algorithmic reasoning with and through graphs, where graphs are posed as a way to represent, reason with and solve a problem. It targets at fostering children’s understanding of abstract graphs through a collaborative problem solving task. 

Concretely, children participating in the experiment interact, in teams, with a setup consisting of two input modalities (mice or/and touch screens or tangible robots called Cellulos) and a humanoid robot such as a QTrobot or a NAO robot, in the presence of an observer. The learning activity allows the children to solve an instance of minimum spanning tree problem along with a robot that is present for motivational support and guidance. For example, in the concrete scenario of a mining company desiring to connect gold mines, the minimum spanning tree problem corresponds to connecting them most effectively in terms of spending as little as possible for building the roads. 

We aim at using the data to model the interaction and then use the model to adapt the behavior of the robot in real time in various research contexts including but not limited to the concepts of engagement, mutual modelling, etc. in an educational setting to improve the learning outcome.

The latest setup as described above focuses on solving an instance of the minimum spanning tree problem with the input modality as the touch screens. However, in the initial phase of this project, a few experiments were conducted in another activity which was in a path planning scenario with Cellulo as the input modality. In that activity, children in pairs were asked to find the best path from a home to a destination, where the learning outcome is to understand the basic notion of cost. More details can be found in the publication titled: “ What Do Human-Robot Interaction Traces Tell Us About Learning ?”.

Studying Alignment in Spontaneous Speech via Automatic Methods: How Do Children Use Task-specific Referents to Succeed in a Collaborative Learning Activity?

U. Norman; T. Dinkar; B. Bruno; C. Clavel 


p. 41.


Mutual Modelling Ability for a Humanoid Robot: How can it improve my learning as we solve a problem together?

U. Norman; B. Bruno; P. Dillenbourg 


Robots for Learning Workshop in 16th annual IEEE/ACM Conference on Human-Robot Interaction (HRI 2021), Virtual Conference, March 9-11, 2021.

A Social Robot That Looks For Productive Engagement

J. Nasir; B. Bruno; P. Dillenbourg 


Robots for Learning workshop at 16th annual ACM/IEEE International Conference on Human-Robot Interaction, Online conference, March 9-11, 2021.

What if Social Robots look for Productive Engagement?

J. Nasir; B. Bruno; M. Chetouani; P. Dillenbourg 

International Journal of Social Robotics


DOI : 10.1007/s12369-021-00766-w

When Positive Perception of the Robot Has No Effect on Learning

J. Nasir; U. Norman; B. Bruno; P. Dillenbourg 

2020 29Th Ieee International Conference On Robot And Human Interactive Communication (Ro-Man)


29th IEEE International Conference on Robot and Human Interactive Communication (IEEE RO-MAN), Virtual Conference, Aug 31 – Sept 4, 2020.

p. 313-320

DOI : 10.1109/RO-MAN47096.2020.9223343

Engagement in Human-Agent Interaction: An Overview

C. Oertel; G. Castellano; M. Chetouani; J. Nasir; M. Obaid et al. 

Frontiers In Robotics And Ai


Vol. 7 , p. 92.

DOI : 10.3389/frobt.2020.00092

Is There ‘ONE way’ of Learning? A Data-driven Approach

J. Nasir; B. Bruno; P. Dillenbourg 


22nd ACM International Conference on Multimodal Interaction, Virtual event, Netherlands, October 25-29, 2020.

You Tell, I Do, and We Swap until we Connect All the Gold Mines!

J. Nasir; U. Norman; B. Bruno; P. Dillenbourg 



Vol. 2020 , num. 120, p. 22-23.

Robot Analytics: What Do Human-Robot Interaction Traces Tell Us About Learning?

J. Nasir; U. Norman; W. Johal; J. K. Olsen; S. Shahmoradi et al. 

2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)


IEEE RoMan 2019 – The 28th IEEE International Conference on Robot & Human Interactive Communication, New Delhi, India, October 14-18, 2019.

DOI : 10.1109/RO-MAN46459.2019.8956465

Orchestration of Robotic Activities in Classrooms: Challenges and Opportunities

S. Shahmoradi; J. K. Olsen; S. Haklev; W. Johal; U. Norman et al. 

Transforming Learning with Meaningful Technologies


p. 640-644

DOI : 10.1007/978-3-030-29736-7_57

Applying IDC theory to education in the Alps region: A response to Chan et al.’s contribution

P. Dillenbourg; K. G. Kim; J. Nasir; S. T. Yeo; J. K. Olsen 

Research and Practice in Technology Enhanced Learning


Vol. 14 , p. 17.

DOI : 10.1186/s41039-019-0111-6

Learning By Collaborative Teaching : An Engaging Multi-Party CoWriter Activity

L. El-Hamamsy; W. Johal; T. L. C. Asselborn; J. Nasir; P. Dillenbourg 

2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)


The 28th IEEE International Conference on Robot & Human Interactive Communication (RoMan 2019), New Delhi, India, October 14 – 18, 2019.

DOI : 10.1109/RO-MAN46459.2019.8956358


This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 765955.